NVIDIA: Nemotron 3 Super (free)
nvidia
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
- Context window
- 262,144 tokens
- Input cost
- $0.09 / 1M
- Output cost
- $0.45 / 1M
- Latency (p50)
- —